Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.7330. Min Act: -0.0000

Data Index: 1271696 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.9342. Min Act: -0.0000

Data Index: 572968 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.7765. Min Act: -0.0000

Data Index: 701784 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.7676. Min Act: -0.0000

Data Index: 197428 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.7610. Min Act: -0.0000

Data Index: 1255806 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.6572. Min Act: -0.0000

Data Index: 1445398 (Python Code)

Max Activating Token Index: 935

Text #6

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.6599. Min Act: -0.0000

Data Index: 666572 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.7411. Min Act: -0.0000

Data Index: 1333381 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.5595. Min Act: -0.0000

Data Index: 1065433 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.5639. Min Act: -0.0000

Data Index: 299313 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.5082. Min Act: -0.0000

Data Index: 1124442 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.3512. Min Act: -0.0000

Data Index: 975561 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.3214. Min Act: -0.0000

Data Index: 1231755 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.4584. Min Act: -0.0000

Data Index: 165426 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.3101. Min Act: -0.0000

Data Index: 324235 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.4393. Min Act: -0.0000

Data Index: 955529 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.4259. Min Act: -0.0000

Data Index: 41063 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.5454. Min Act: -0.0000

Data Index: 739259 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.3046. Min Act: -0.0000

Data Index: 1194401 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 2.9342. Min Range: -2.9342

Max Act: 2.5131. Min Act: -0.0000

Data Index: 1262406 (C4 (Web Text))

Max Activating Token Index: 84